Chang Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Interests
Chang Liu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jianmin Li
Zhejiang Chinese Medical University and Gancao Doctor Chinese Medicine Artificial Intelligence Joint Engineering Center, Zhejiang Chinese Medical University, Hangzhou, China
2 shared publications - Lingyong Cao
School of Basic Medical Sciences, Zhejiang Chinese Medical University, Hangzhou, China
2 shared publications - Qing Han
Zhejiang Chinese Medical University
2 shared publications - Shuyuan Lin
School of Basic Medical Sciences, Zhejiang Chinese Medical University
2 shared publications - Ying Chang
School of Basic Medical Sciences, Zhejiang Chinese Medical University, Hangzhou, China
2 shared publications - Yiqian Qu
School of Basic Medical Sciences, Zhejiang Chinese Medical University, Hangzhou, China
2 shared publications
Latest Publications
- Open Access
- 2 August 2024
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 12, e55090
Research on Traditional Chinese Medicine: Domain Knowledge Graph Completion and Quality Evaluation
Background: Knowledge graphs (KGs) can integrate domain knowledge into a traditional Chinese medicine (TCM) intelligent syndrome differentiation model. However, the quality of current KGs in the TCM domain varies greatly, related to the lack of knowledge graph completion (KGC) and evaluation methods. Objective: This study aims to investigate KGC and evaluation methods tailored for TCM domain knowledge. Methods: In the KGC phase, according to the characteristics of TCM domain knowledge, we proposed a 3-step “entity-ontology-path” completion approach. This approach uses path reasoning, ontology rule reasoning, and association rules. In the KGC quality evaluation phase, we proposed a 3-dimensional evaluation framework that encompasses completeness, accuracy, and usability, using quantitative metrics such as complex network analysis, ontology reasoning, and graph representation. Furthermore, we compared the impact of different graph representation models on KG usability. Results: In the KGC phase, 52, 107, 27, and 479 triples were added by outlier analysis, rule-based reasoning, association rules, and path-based reasoning, respectively. In addition, rule-based reasoning identified 14 contradictory triples. In the KGC quality evaluation phase, in terms of completeness, KG had higher density and lower sparsity after completion, and there were no contradictory rules within the KG. In terms of accuracy, KG after completion was more consistent with prior knowledge. In terms of usability, the mean reciprocal ranking, mean rank, and hit rate of the first N tail entities predicted by the model (Hits@N) of the TransE, RotatE, DistMult, and ComplEx graph representation models all showed improvement after KGC. Among them, the RotatE model achieved the best representation. Conclusions: The 3-step completion approach can effectively improve the completeness, accuracy, and availability of KGs, and the 3-dimensional evaluation framework can be used for comprehensive KGC evaluation. In the TCM field, the RotatE model performed better at KG representation.
- 2 August 2024
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 12, e55090
Open AccessResearch on Traditional Chinese Medicine: Domain Knowledge Graph Completion and Quality Evaluation
Background: Knowledge graphs (KGs) can integrate domain knowledge into a traditional Chinese medicine (TCM) intelligent syndrome differentiation model. However, the quality of current KGs in the TCM domain varies greatly, related to the lack of knowledge graph completion (KGC) and evaluation methods. Objective: This study aims to investigate KGC and evaluation methods tailored for TCM domain knowledge. Methods: In the KGC phase, according to the characteristics of TCM domain knowledge, we proposed a 3-step “entity-ontology-path” completion approach. This approach uses path reasoning, ontology rule reasoning, and association rules. In the KGC quality evaluation phase, we proposed a 3-dimensional evaluation framework that encompasses completeness, accuracy, and usability, using quantitative metrics such as complex network analysis, ontology reasoning, and graph representation. Furthermore, we compared the impact of different graph representation models on KG usability. Results: In the KGC phase, 52, 107, 27, and 479 triples were added by outlier analysis, rule-based reasoning, association rules, and path-based reasoning, respectively. In addition, rule-based reasoning identified 14 contradictory triples. In the KGC quality evaluation phase, in terms of completeness, KG had higher density and lower sparsity after completion, and there were no contradictory rules within the KG. In terms of accuracy, KG after completion was more consistent with prior knowledge. In terms of usability, the mean reciprocal ranking, mean rank, and hit rate of the first N tail entities predicted by the model (Hits@N) of the TransE, RotatE, DistMult, and ComplEx graph representation models all showed improvement after KGC. Among them, the RotatE model achieved the best representation. Conclusions: The 3-step completion approach can effectively improve the completeness, accuracy, and availability of KGs, and the 3-dimensional evaluation framework can be used for comprehensive KGC evaluation. In the TCM field, the RotatE model performed better at KG representation.
- Open Access
- 2 December 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Research on Traditional Chinese Medicine: Domain Knowledge Graph Completion and Quality Evaluation (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Knowledge graphs (KGs) can integrate domain knowledge into a traditional Chinese medicine (TCM) intelligent syndrome differentiation model. However, the quality of current KGs in the TCM domain varies greatly, related to the lack of knowledge graph completion (KGC) and evaluation methods. Objective: This study aims to investigate KGC and evaluation methods tailored for TCM domain knowledge. Methods: In the KGC phase, according to the characteristics of TCM domain knowledge, we proposed a 3-step “entity-ontology-path” completion approach. This approach uses path reasoning, ontology rule reasoning, and association rules. In the KGC quality evaluation phase, we proposed a 3-dimensional evaluation framework that encompasses completeness, accuracy, and usability, using quantitative metrics such as complex network analysis, ontology reasoning, and graph representation. Furthermore, we compared the impact of different graph representation models on KG usability. Results: In the KGC phase, 52, 107, 27, and 479 triples were added by outlier analysis, rule-based reasoning, association rules, and path-based reasoning, respectively. In addition, rule-based reasoning identified 14 contradictory triples. In the KGC quality evaluation phase, in terms of completeness, KG had higher density and lower sparsity after completion, and there were no contradictory rules within the KG. In terms of accuracy, KG after completion was more consistent with prior knowledge. In terms of usability, the mean reciprocal ranking, mean rank, and hit rate of the first N tail entities predicted by the model (Hits@N) of the TransE, RotatE, DistMult, and ComplEx graph representation models all showed improvement after KGC. Among them, the RotatE model achieved the best representation. Conclusions: The 3-step completion approach can effectively improve the completeness, accuracy, and availability of KGs, and the 3-dimensional evaluation framework can be used for comprehensive KGC evaluation. In the TCM field, the RotatE model performed better at KG representation.
- 2 December 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessResearch on Traditional Chinese Medicine: Domain Knowledge Graph Completion and Quality Evaluation (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Knowledge graphs (KGs) can integrate domain knowledge into a traditional Chinese medicine (TCM) intelligent syndrome differentiation model. However, the quality of current KGs in the TCM domain varies greatly, related to the lack of knowledge graph completion (KGC) and evaluation methods. Objective: This study aims to investigate KGC and evaluation methods tailored for TCM domain knowledge. Methods: In the KGC phase, according to the characteristics of TCM domain knowledge, we proposed a 3-step “entity-ontology-path” completion approach. This approach uses path reasoning, ontology rule reasoning, and association rules. In the KGC quality evaluation phase, we proposed a 3-dimensional evaluation framework that encompasses completeness, accuracy, and usability, using quantitative metrics such as complex network analysis, ontology reasoning, and graph representation. Furthermore, we compared the impact of different graph representation models on KG usability. Results: In the KGC phase, 52, 107, 27, and 479 triples were added by outlier analysis, rule-based reasoning, association rules, and path-based reasoning, respectively. In addition, rule-based reasoning identified 14 contradictory triples. In the KGC quality evaluation phase, in terms of completeness, KG had higher density and lower sparsity after completion, and there were no contradictory rules within the KG. In terms of accuracy, KG after completion was more consistent with prior knowledge. In terms of usability, the mean reciprocal ranking, mean rank, and hit rate of the first N tail entities predicted by the model (Hits@N) of the TransE, RotatE, DistMult, and ComplEx graph representation models all showed improvement after KGC. Among them, the RotatE model achieved the best representation. Conclusions: The 3-step completion approach can effectively improve the completeness, accuracy, and availability of KGs, and the 3-dimensional evaluation framework can be used for comprehensive KGC evaluation. In the TCM field, the RotatE model performed better at KG representation.
- 13 December 2021
- Published by SAGE Publications in Acupuncture in Medicine
- Vol. 40 (4) , 289-298
Effect of acupuncture on menopausal hot flushes and serum hormone levels: a systematic review and meta-analysis
Objective: To evaluate the efficacy/effectiveness and safety of acupuncture for the treatment of hot flushes and its impact on serum hormone levels in menopausal women. Methods: A total of 10 databases were searched from their inception to August 2018. Reference lists of reviews and included articles were also hand-searched. Randomized controlled trials (RCTs) comparing the effect of acupuncture versus sham acupuncture, or acupuncture versus hormone therapy (HT), as treatment for menopausal hot flushes were included. Outcomes included hot flush frequency, hot flush severity and serum hormone levels of estradiol (E2), luteinizing hormone (LH) and follicle-stimulating hormone (FSH). Meta-analyses were performed using Review Manager 5.3 software. Results: Thirteen RCTs including 1784 patients were selected, seven of which were available for meta-analysis. Compared with sham acupuncture, acupuncture significantly decreased hot flush frequency (mean difference (MD) −0.84, 95% confidence interval (CI) [−1.64, −0.05], I 2 = 54%) from baseline to the end of study, but did not impact end scores of hot flush frequency (MD 0.19, 95% CI [−0.61, 0.99], I 2 = 0%) or severity (MD 0.02, 95% CI [−0.13, 0.17], I 2 = 0%). No differences were found between acupuncture and HT in serum levels of E 2 (MD 6.56, 95% CI [−3.77, 16.89], I 2 = 76%), FSH (MD 1.06, 95% CI [−1.44, 3.56], I 2 = 0%) or LH (MD −3.36, 95% CI [−13.37, 6.65], I 2 = 89%). Conclusion: Acupuncture may not decrease hot flush frequency, but yet appears to have similar effects on serum hormone levels as HT, that is, increased E2 and decreased FSH and LH. Considering that no firm conclusions could be drawn due to the low quality and limited number of included trials included, further high-quality RCTs need to be conducted.
- 13 December 2021
- Published by SAGE Publications in Acupuncture in Medicine
- Vol. 40 (4) , 289-298
Effect of acupuncture on menopausal hot flushes and serum hormone levels: a systematic review and meta-analysis
Objective: To evaluate the efficacy/effectiveness and safety of acupuncture for the treatment of hot flushes and its impact on serum hormone levels in menopausal women. Methods: A total of 10 databases were searched from their inception to August 2018. Reference lists of reviews and included articles were also hand-searched. Randomized controlled trials (RCTs) comparing the effect of acupuncture versus sham acupuncture, or acupuncture versus hormone therapy (HT), as treatment for menopausal hot flushes were included. Outcomes included hot flush frequency, hot flush severity and serum hormone levels of estradiol (E2), luteinizing hormone (LH) and follicle-stimulating hormone (FSH). Meta-analyses were performed using Review Manager 5.3 software. Results: Thirteen RCTs including 1784 patients were selected, seven of which were available for meta-analysis. Compared with sham acupuncture, acupuncture significantly decreased hot flush frequency (mean difference (MD) −0.84, 95% confidence interval (CI) [−1.64, −0.05], I 2 = 54%) from baseline to the end of study, but did not impact end scores of hot flush frequency (MD 0.19, 95% CI [−0.61, 0.99], I 2 = 0%) or severity (MD 0.02, 95% CI [−0.13, 0.17], I 2 = 0%). No differences were found between acupuncture and HT in serum levels of E 2 (MD 6.56, 95% CI [−3.77, 16.89], I 2 = 76%), FSH (MD 1.06, 95% CI [−1.44, 3.56], I 2 = 0%) or LH (MD −3.36, 95% CI [−13.37, 6.65], I 2 = 89%). Conclusion: Acupuncture may not decrease hot flush frequency, but yet appears to have similar effects on serum hormone levels as HT, that is, increased E2 and decreased FSH and LH. Considering that no firm conclusions could be drawn due to the low quality and limited number of included trials included, further high-quality RCTs need to be conducted.